Part 2.1: Features Engineering and Visualitions

This phase focuses on enhancing the dataset by creating meaningful features that capture temporal patterns, store-specific behaviors, customers and sales analysis. It also includes visual exploration to uncover trends, seasonality, and anomalies—laying the groundwork for robust forecasting models.

1. Setup & Imports Libraries

---

import time 

# Step 1: Setup & Imports Libraries
print("Step 1: Setup and Import Libraries started...")
time.sleep(1)  # Simulate processing time

Step 1: Setup and Import Libraries started...

# Data Manipulation & Processing
import math
import numpy as np
import pandas as pd
from pathlib import Path
import scipy.stats as stats
from datetime import datetime
from sklearn.preprocessing import *

# Data Visualization
import seaborn as sbn
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker

import plotly.io as pio
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots

from pandas.plotting import scatter_matrix

# to ensure Plotly works in both Jupyter and HTML export
pio.renderers.default = "notebook+plotly_mimetype"

sbn.set(rc={'figure.figsize':(14,6)})
plt.style.use('seaborn-v0_8')
sbn.set_palette("husl")

# Set display options
pd.set_option('display.max_columns', None)
pd.set_option('display.width', 1000)
pd.set_option('display.float_format','{:.2f}'.format)

# Warnings
import warnings
warnings.simplefilter('ignore')
warnings.filterwarnings('ignore')

print("="*60)
print("Rossman Store Sales Time Series Analysis - Part 2")
print("="*60)
print("All libraries imported successfully!")
print("Analysis Date:", pd.Timestamp.now().strftime('%Y-%m-%d %H:%M:%S'))

============================================================
Rossman Store Sales Time Series Analysis - Part 2
============================================================
All libraries imported successfully!
Analysis Date: 2025-08-13 21:14:32

print("✅ Setup and Import Liraries completed.\n")

✅ Setup and Import Liraries completed.

# Start analysis

data_viz_begin = pd.Timestamp.now()

bold_start = '\033[1m'
bold_end = '\033[0m'

print("🔍 Part 2 Started ...")
print(f"🟢 Begin Date: {bold_start}{data_viz_begin.strftime('%Y-%m-%d %H:%M:%S')}{bold_end}\n")

🔍 Part 2 Started ...
🟢 Begin Date: 2025-08-13 21:14:32

Restore the file

---

%store -r df_viz_feat

View or Display Dataset

print("\nTrain Data Preview:")
print("\n",df_viz_feat.head())

Train Data Preview:

         store  dayofweek       date  sales  customers  open     promo stateholiday  schoolholiday  day  week month  quarter  year  isweekend  isholiday  isschoolDay
982643   1115          2 2013-01-01      0          0     0  No Promo       Public              1  Tue     1   Jan        1  2013      False       True        False
982640   1112          2 2013-01-01      0          0     0  No Promo       Public              1  Tue     1   Jan        1  2013      False       True        False
982639   1111          2 2013-01-01      0          0     0  No Promo       Public              1  Tue     1   Jan        1  2013      False       True        False
982638   1110          2 2013-01-01      0          0     0  No Promo       Public              1  Tue     1   Jan        1  2013      False       True        False
982637   1109          2 2013-01-01      0          0     0  No Promo       Public              1  Tue     1   Jan        1  2013      False       True        False

2. Data Visualization

---

# Step 1: Setup & Imports Libraries
print("Step 2: Data Visualization started...")
time.sleep(1)  # Simulate processing time

Step 2: Data Visualization started...

Percentage Distribution per Open

# Count frequency of each unique value
value_counts = df_viz_feat['open'].value_counts()

# Map numeric labels to descriptive ones using if-else logic
labels = ["Open" if val == 1 else "Closed" for val in value_counts.index]
values = value_counts.values.tolist()

# Dynamically create 'pull' values to highlight the largest slice
pull = [0.1 if i == 0 else 0 for i in range(len(labels))]

# Create pie chart
fig = go.Figure(data=[go.Pie(
    labels=labels,
    values=values,
    pull=pull,
    textinfo='percent+label',
    hoverinfo='label+value+percent'
)])

# Update layout with left-aligned title
fig.update_layout(
    title_text='📊 Store Status Distribution: Open vs Closed',
    title_x=0.0,  # Left-aligned title
    showlegend=True,
    width=1200,    # Increased width
    height=450    # Increased height
)

fig.show(config={'displayModeBar': True, 'displaylogo': False})

# export_plotly_chart(fig, name="open_vs_closed_pie")

Percentage Distribution with Respect to Promo

# Get value counts (Series), extracting both labels and values in matching order
counts = df_viz_feat['promo'].value_counts()
labels = counts.index.tolist()
values = counts.values.tolist()

# Create a 'pull' list to highlight the first class, rest unpulled
pull = [0.1 if i == 0 else 0 for i in range(len(labels))]

# Create the pie chart
fig = go.Figure(
    data =[go.Pie(
        labels = labels,
        values = values,
        pull = pull,
        textinfo ='percent+label',
        insidetextorientation ='radial',
    )]
)

# Update the layout to fix title overlap
fig.update_layout(
    title_text ='📊 % Distribution per Promo',
    title_x = 1.0,  # Centered title
    title_font_size = 20,  # Optional: adjust font size
    margin = dict(t = 60, r = 60, b = 60, l = 60),  # Increased top margin
    width = 1200,
    height = 450
)

fig.show(config={'displayModeBar': True, 'displaylogo': False})

# export_plotly_chart(fig, name="promo_pie")

Percentage Distribution per Holiday Type

# Get value counts (Series), extracting both labels and values in matching order
counts = df_viz_feat['stateholiday'].value_counts()
labels = counts.index.tolist()
values = counts.values.tolist()

# Create a 'pull' list to highlight the first class, rest unpulled
pull = [0.1 if i == 0 else 0 for i in range(len(labels))]

# Create the pie chart
fig = go.Figure(
    data =[go.Pie(
        labels = labels,
        values = values,
        pull = pull,
        textinfo ='percent+label',
        insidetextorientation ='radial',
    )]
)

# Update the layout to fix title overlap
fig.update_layout(
    title_text ='📊 % Distribution per State Holiday',
    title_x = 1.0,  # Centered title
    title_font_size = 20,  # Optional: adjust font size
    margin = dict(t = 60, r = 60, b = 60, l = 60),  # Increased top margin
    width = 1200,
    height = 450
)

fig.show(config={'displayModeBar': True, 'displaylogo': False})

# export_plotly_chart(fig, name="sateholiday_pie")

Percentage Distribution per School Holiday

# Efficient value counting and labeling
counts = df_viz_feat['schoolholiday'].value_counts().sort_index()
labels = ['No School Holiday', 'School Holiday']  # Assumes 0=no, 1=yes
values = counts.values

# Create donut chart
fig = go.Figure(data=go.Pie(
    labels=labels,
    values=values,
    pull=[0, 0.1],  # Emphasize 'School Holiday' slice
    hole=0.3,
    textinfo='label+percent',
    marker=dict(colors=['#4ECDC4', '#FF6B6B'], line=dict(color='#FFFFFF', width=2))
))

# Layout for clarity and aesthetics
fig.update_layout(
    title_text = '📊 % Distribution per School Holiday',
    title_x = 0.5,
    font = dict(size = 12, family = 'Arial, sans-serif'),
    margin = dict(t = 60, b = 40, l = 40, r = 100),
    width = 1200,
    height = 450,
    showlegend  =True
)

# Annotation for total records
fig.add_annotation(
    text = f"Total Records: {len(df_viz_feat):,}",
    x = 0.5,
    y =- 0.1,
    xref ="paper",
    yref = "paper",
    showarrow = False,
    font = dict(size = 10, color="gray")
)

fig.show(config={'displayModeBar': True, 'displaylogo': False})

# export_plotly_chart(fig, name="schoolholiday_pie")

Customer Analysis

Average Customers Trend per Day

# Define weekday order
weekday_order = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']

# Calculate mean sales by day
dow_agg = df_viz_feat.groupby('day')['customers'].mean().reset_index()

# Apply categorical ordering
dow_agg['day'] = pd.Categorical(dow_agg['day'], categories=weekday_order, ordered=True)
dow_agg = dow_agg.sort_values('day')

# Create simple line chart
fig = px.line(
    dow_agg, 
    x = 'day', 
    y ='customers', 
    title ='📈 Average Customers by Day of Week',
    markers = True
)

# Simple styling
fig.update_layout(
    title={'x': 0.5, 'xanchor': 'center'},
    xaxis_title ='Day of Week',
    yaxis_title ='Average Customers',
)

# Find peak for simple annotation
peak_idx = dow_agg['customers'].idxmax()
peak_day = dow_agg.loc[peak_idx, 'day']
peak_value = dow_agg.loc[peak_idx, 'customers']

# Simple annotation
fig.add_annotation(
    x = peak_day,
    y = peak_value,
    text = f"Peak: {peak_day} ({peak_value:.0f})",
    showarrow = True,
    arrowcolor ='red',
    font = dict(color = 'red')
)

fig.update_layout(margin=dict(t=60, r=40, b=40, l=40),  width = 1200,height = 400)
fig.show(config={'displayModeBar': True, 'displaylogo': False})

print("Daily Sales Data:")
print(dow_agg)

# export_plotly_chart(fig, name="daily_avg_customers_trend")

Daily Sales Data:
   day  customers
1  Mon     812.93
5  Tue     761.86
6  Wed     721.20
4  Thu     695.78
0  Fri     742.53
2  Sat     658.76
3  Sun      35.58

Average Customers Trend per Month

# Ensure month is ordered
month_order = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun','Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']

monthly_grp = df_viz_feat.groupby('month', as_index=False)['customers'].mean()
monthly_grp['month'] = pd.Categorical(monthly_grp['month'], categories=month_order, ordered=True)
monthly_grp = monthly_grp.sort_values('month')

# Identify peak
peak_row = monthly_grp.loc[monthly_grp['customers'].idxmax()]
peak_month = peak_row['month']
peak_value = peak_row['customers']

# Create Plotly Express line plot
fig = px.line(monthly_grp, x='month', y='customers',
              markers=True,
              title='📈  Average Customers Trend per Month',
              labels={'customers': 'Average Customers', 'month': 'Month'},
              line_shape='linear')  # You can switch to 'spline' for smooth curves

# Annotate peak
fig.add_annotation(x=peak_month, y=peak_value,
                   text=f'Peak: {peak_month} ({peak_value:.1f})',
                   showarrow=True,
                   arrowhead=2,
                   arrowsize=1,
                   arrowwidth=2,
                   arrowcolor='red',
                   font=dict(color='red', size=12),
                   yshift=15)

fig.update_layout(margin=dict(t=60, r=40, b=40, l=40),width = 1200,height = 450)
fig.show(config={'displayModeBar': True, 'displaylogo': False})

# export_plotly_chart(fig, name="monthly_avg_customers_trend")

Sales Analysis

Average SalesTrend per Day

# Define weekday order
weekday_order = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']

# Calculate mean sales by day
dow_agg = df_viz_feat.groupby('day')['sales'].mean().reset_index()

# Apply categorical ordering
dow_agg['day'] = pd.Categorical(dow_agg['day'], categories=weekday_order, ordered=True)
dow_agg = dow_agg.sort_values('day')

# Create simple line chart
fig = px.line(
    dow_agg, 
    x = 'day', 
    y ='sales', 
    title ='📈 Average Sales by Day of Week',
    markers = True
)

# Simple styling
fig.update_layout(
    title={'x': 0.5, 'xanchor': 'center'},
    xaxis_title ='Day of Week',
    yaxis_title ='Average Sales',
)

# Find peak for simple annotation
peak_idx = dow_agg['sales'].idxmax()
peak_day = dow_agg.loc[peak_idx, 'day']
peak_value = dow_agg.loc[peak_idx, 'sales']

# Simple annotation
fig.add_annotation(
    x = peak_day,
    y = peak_value,
    text = f"Peak: {peak_day} ({peak_value:.0f})",
    showarrow = True,
    arrowcolor ='red',
    font = dict(color = 'red')
)

fig.update_layout(margin=dict(t=60, r=40, b=40, l=40), width = 1200,height = 400)
fig.show(config={'displayModeBar': True, 'displaylogo': False})

# export_plotly_chart(fig, name="daily_avg_sales_trend")

Average Sales Trend per Month

# Ensure month is ordered
month_order = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun','Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']

monthly_grp = df_viz_feat.groupby('month', as_index=False)['sales'].mean()
monthly_grp['month'] = pd.Categorical(monthly_grp['month'], categories=month_order, ordered=True)
monthly_grp = monthly_grp.sort_values('month')

# Identify peak
peak_row = monthly_grp.loc[monthly_grp['sales'].idxmax()]
peak_month = peak_row['month']
peak_value = peak_row['sales']

# Create Plotly Express line plot
fig = px.line(monthly_grp, x='month', y='sales',
              markers=True,
              title='📈  Average Sales Trend per Month',
              labels={'sales': 'Average Sales', 'month': 'Month'},
              line_shape='linear')  # You can switch to 'spline' for smooth curves

# Annotate peak
fig.add_annotation(x=peak_month, y=peak_value,
                   text=f'Peak: {peak_month} ({peak_value:.1f})',
                   showarrow=True,
                   arrowhead=2,
                   arrowsize=1,
                   arrowwidth=2,
                   arrowcolor='red',
                   font=dict(color='red', size=12),
                   yshift=15)

fig.update_layout(margin=dict(t=60, r=40, b=40, l=40),width = 1200,height = 450)
fig.show(config={'displayModeBar': True, 'displaylogo': False})

# export_plotly_chart(fig, name="montly_avg_sales_trend")

Box Plots by Time Segment

# Box plot by Month
fig1 = px.box(
    df_viz_feat, 
    x='month', 
    y='sales',
    title='Sales Distribution by Month',
    category_orders={'month': ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun','Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']}
)
fig1.update_layout(title_x=0.5, width = 1200,height=500)
fig1.show()

# Box plot by Day of Week  
fig2 = px.box(
    df_viz_feat, 
    x='day', 
    y='sales',
    title='Sales Distribution by Day of Week',
    category_orders={'day': ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']}
)
fig2.update_layout(title_x=0.5, width = 1200,height=500)
fig2.show()

# Box plot by Year
fig3 = px.box(
    df_viz_feat, 
    x='year', 
    y='sales',
    title='Sales Distribution by Year'
)
fig3.update_layout(title_x=0.5, width = 1200,height = 500)
fig.show(config={'displayModeBar': True, 'displaylogo': False})

# Simple summary statistics
print("Sales Distribution Summary by Category:")
print("=" * 45)

print("\nBy Month:")
monthly_stats = df_viz_feat.groupby('month')['sales'].agg(['mean', 'median', 'std']).round(0)
for month, stats in monthly_stats.iterrows():
    print(f"{month}: Mean=€{stats['mean']:,.0f}, Median=€{stats['median']:,.0f}")

print("\nBy Day:")
daily_stats = df_viz_feat.groupby('day')['sales'].agg(['mean', 'median', 'std']).round(0)
for day, stats in daily_stats.iterrows():
    print(f"{day}: Mean=€{stats['mean']:,.0f}, Median=€{stats['median']:,.0f}")

Sales Distribution Summary by Category:
=============================================

By Month:
Apr: Mean=€5,739, Median=€5,718
Aug: Mean=€5,693, Median=€5,633
Dec: Mean=€6,827, Median=€6,728
Feb: Mean=€5,645, Median=€5,610
Jan: Mean=€5,465, Median=€5,483
Jul: Mean=€6,023, Median=€5,878
Jun: Mean=€5,761, Median=€5,729
Mar: Mean=€5,785, Median=€5,750
May: Mean=€5,490, Median=€5,717
Nov: Mean=€6,008, Median=€6,081
Oct: Mean=€5,537, Median=€5,567
Sep: Mean=€5,570, Median=€5,504

By Day:
Fri: Mean=€6,704, Median=€6,422
Mon: Mean=€7,798, Median=€7,300
Sat: Mean=€5,857, Median=€5,419
Sun: Mean=€203, Median=€0
Thu: Mean=€6,216, Median=€5,995
Tue: Mean=€7,006, Median=€6,463
Wed: Mean=€6,536, Median=€6,115

print("✅ Data Visualization completed.\n")

✅ Data Visualization completed.

---

print("✅ Features Engineering and Data Visualization (I) completed successfully!")
print(f"🗓️ Analysis Date: {bold_start}{pd.Timestamp.now().strftime('%Y-%m-%d %H:%M:%S')}{bold_end}")

✅ Features Engineering and Data Visualization (I) completed successfully!
🗓️ Analysis Date: 2025-08-13 21:14:39

# End analysis
data_viz_end = pd.Timestamp.now()
duration = data_viz_end - data_viz_begin

# Final summary print
print("\n📋 Features Engineering && Data Viz Summary")
print(f"🟢 Begin Date: {bold_start}{data_viz_begin.strftime('%Y-%m-%d %H:%M:%S')}{bold_end}")
print(f"✅ End Date:   {bold_start}{data_viz_end.strftime('%Y-%m-%d %H:%M:%S')}{bold_end}")
print(f"⏱️ Duration:   {bold_start}{str(duration)}{bold_end}")

📋 Features Engineering && Data Viz Summary
🟢 Begin Date: 2025-08-13 21:14:32
✅ End Date:   2025-08-13 21:14:39
⏱️ Duration:   0 days 00:00:06.645794

---

Project Design Rationale: Notebook Separation

To promote clarity, maintainability, and scalability within the project,Visualization Impact Analysis tasks are intentionally separated into distinct notebooks. This modular approach prevents the accumulation of excessive code in a single notebook, making it easier to debug, update, and collaborate across different stages of the workflow. By isolating data transformation logic from visual analysis, each notebook remains focused and purpose-driven, ultimately enhancing the overall efficiency and readability of the project.